New global asymptotic stability of discrete-time recurrent neural networks with multiple time-varying delays in the leakage term and impulsive effects

被引：20

作者：

Balasundaram, K. ^{[1
]}

Raja, R. ^{[2
]}

Zhu, Quanxin ^{[3
,4
,5
]}

Chandrasekaran, S. ^{[6
]}

Zhou, Hongwei ^{[7
]}

机构：

[1] Sri Vijay Vidyalaya Coll Arts & Sci, Dept Math, Dharmapuri 636807, India

[2] Alagappa Univ, Ramanujan Ctr Higher Math, Karaikkudi 630004, Tamil Nadu, India

[3] Nanjing Normal Univ, Sch Math Sci, Nanjing 210023, Jiangsu, Peoples R China

[4] Nanjing Normal Univ, Inst Finance & Stat, Nanjing 210023, Jiangsu, Peoples R China

[5] Univ Bielefeld, Dept Math, D-33615 Bielefeld, Germany

[6] Khadir Mohideen Coll, Dept Math, Adirampattinam 614701, Thanjavur, India

[7] Nanjing Xiaozhuang Univ, Sch Math & Informat Technol, Nanjing 211171, Jiangsu, Peoples R China

来源：

NEUROCOMPUTING | 2016年 / 214卷

基金：

中国国家自然科学基金;

关键词：

Leakage delay; Asymptotic stability; Recurrent neural network; Delay-dependent; Linear matrix inequality; Impulse; Time-varying delay; EXPONENTIAL STABILITY; NEUTRAL-TYPE; DEPENDENT STABILITY; DISTRIBUTED DELAYS; PASSIVITY ANALYSIS; CRITERIA; ANALOGS;

D O I：

10.1016/j.neucom.2016.06.040

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper investigates the problem of discrete-time stochastic recurrent neural networks with multiple time-varying delays in the leakage terms and impulses. A new set of sufficient conditions are obtained by constructing an appropriate Lyapunov-Krasovskii functional combining with linear matrix inequality technique and free weighting matrix method. The obtained delay-dependent stability conditions are expressed in terms of linear matrix inequalities and it can be solved via some available software packages. Up to now, the asymptotic stability problem is studied for discrete-delay in the leakage terms. For the first time in our paper, we have considered distributed delays and impulses for such kind of networks. In addition, we have provided a numerical example to demonstrate the effectiveness of our obtained stability results for the theoretical section. (C) 2016 Elsevier B.V. All rights reserved.

引用

页码：420 / 429

页数：10

共 36 条

[21] Exponential stability of continuous-time and discrete-time cellular neural networks with delays [J].

Mohamad, S ;

Gopalsamy, K .

APPLIED MATHEMATICS AND COMPUTATION, 2003, 135 (01) :17-38

[22] Discrete-time analogues of integrodifferential equations modelling bidirectional neural networks [J].

Mohamad, S ;

Naim, AG .

JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS, 2002, 138 (01) :1-20

[23] Exponential stability preservation in discrete-time analogues of artificial neural networks with distributed delays [J].

Mohamad, Sannay .

JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS, 2008, 215 (01) :270-287

[24] Stability analysis of discrete-time stochastic neural networks with time-varying delays [J].

Ou, Yan ;

Liu, Hongyang ;

Si, Yulin ;

Feng, Zhiguang .

NEUROCOMPUTING, 2010, 73 (4-6) :740-748

[25] EXPONENTIAL STABILITY FOR STOCHASTIC NEURAL NETWORKS OF NEUTRAL TYPE WITH IMPULSIVE EFFECTS [J].

Sakthivel, Rathinasamy ;

Samidurai, R. ;

Anthoni, S. Marshal .

MODERN PHYSICS LETTERS B, 2010, 24 (11) :1099-1110

[26] Global asymptotic stability of BAM neural networks with mixed delays and impulses [J].

Samidurai, R. ;

Sakthivel, R. ;

Anthoni, S. M. .

APPLIED MATHEMATICS AND COMPUTATION, 2009, 212 (01) :113-119

[27] Stability analysis of impulsive stochastic Cohen-Grossberg neural networks with mixed time delays [J].

Song, Qiankun ;

Wang, Zidong .

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2008, 387 (13) :3314-3326

[28] A delay-dependent LMI approach to dynamics analysis of discrete-time recurrent neural networks with time-varying delays [J].

Song, Qiankun ;

Wang, Zidong .

PHYSICS LETTERS A, 2007, 368 (1-2) :134-145

[29] EXISTENCE AND GLOBAL EXPONENTIAL STABILITY OF PERIODIC SOLUTION OF CELLULAR NEURAL NETWORKS WITH IMPULSES AND LEAKAGE DELAY [J].

Wang, Hui ;

Li, Chuandong ;

Xu, Hongbing .

INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS, 2009, 19 (03) :831-842

[30] Sufficient and necessary conditions for global exponential stability of discrete-time recurrent neural networks [J].

Wang, Lisheng ;

Xu, Zongben .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2006, 53 (06) :1373-1380

← 1 2 3 4 →